SOURCE-LINKED INTELLIGENCE

Trajectory as the Teacher: Few-Step Discrete Flow Matching via Energy-Navigated Distillation

Apple Machine Learning Research · article · Sep 16, 2026 · UTC

Discrete flow matching generates text by iteratively transforming noise tokens into coherent language, but may require hundreds of forward passes. Distillation uses the multi-step trajectory to train a student to reproduce the process in a few steps. When the student underperforms, the usual explanation is insufficient capacity. We argue the opposite: the trajectory is the bottleneck, not the student. Each training trajectory is built through a chain of blind stochastic jumps with no evaluation of sequence quality; a single bad decision at an early midpoint propagates through subsequent steps…

Read original source ↗ Open in workspace

recordType

article

region

Global